UNIPO is the first unified interactive visualization tool exposing token-level training dynamics of RL fine-tuning algorithms for LLMs through high-level overviews, step inspectors, and side-by-side comparisons.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
A survey of 457 papers yields a six-dimensional design space for abstraction in interactive systems that reframes gulfs of execution and evaluation while articulating cognitive and design processes for bridging abstraction gaps.
GFlowState introduces interactive visualizations such as trajectory node-link diagrams and transition heatmaps to make GFlowNet training dynamics observable for debugging and quality assessment.
HOLE applies persistent homology to latent embeddings in neural networks and uses visualizations such as cluster flow diagrams to reveal patterns of class separation, feature disentanglement, and robustness.
HCI researchers designed a museum exhibit using feminist data theories to introduce data through a personal, handmade 'hugging_face vibe' distinct from traditional science displays, along with four design choices for creating such vibes.
citing papers explorer
-
HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability
HOLE applies persistent homology to latent embeddings in neural networks and uses visualizations such as cluster flow diagrams to reveal patterns of class separation, feature disentanglement, and robustness.